| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00024397186191192616, | |
| "eval_steps": 3, | |
| "global_step": 3, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 8.132395397064206e-05, | |
| "grad_norm": 0.011654906906187534, | |
| "learning_rate": 2e-05, | |
| "loss": 11.9317, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 8.132395397064206e-05, | |
| "eval_loss": 11.933029174804688, | |
| "eval_runtime": 18.7625, | |
| "eval_samples_per_second": 275.976, | |
| "eval_steps_per_second": 137.988, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00016264790794128412, | |
| "grad_norm": 0.010800319723784924, | |
| "learning_rate": 4e-05, | |
| "loss": 11.9352, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00024397186191192616, | |
| "grad_norm": 0.00888215471059084, | |
| "learning_rate": 6e-05, | |
| "loss": 11.9322, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00024397186191192616, | |
| "eval_loss": 11.933025360107422, | |
| "eval_runtime": 19.13, | |
| "eval_samples_per_second": 270.675, | |
| "eval_steps_per_second": 135.337, | |
| "step": 3 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 354484224.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |